Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the word "able"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parents
    -0.71
     Tradition
    -0.70
     Kendall
    -0.60
    email
    -0.59
    rium
    -0.58
     secrecy
    -0.56
     Bots
    -0.55
     Nose
    -0.55
    aternity
    -0.55
     laundry
    -0.55
    POSITIVE LOGITS
    bodied
    1.09
    ioned
    0.93
    't
    0.90
    reys
    0.77
    Reviewer
    0.75
     bod
    0.74
    istically
    0.71
    iary
    0.71
     afford
    0.70
     compe
    0.69
    Act Density 0.100%

    No Known Activations